Cloud Fleet and Asset Management for Low-Latency Edge AI

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing cloud computing architectures face challenges in latency, bandwidth usage, data privacy, network security, and the capacity to process large volumes of data in real-time for AI and ML workloads, particularly in decentralized edge computing environments.

Innovation Solution

Implementing a fleet management system for edge compute units and connected assets, utilizing a remote fleet management GUI for monitoring and configuring edge devices, and a cloud-based management platform for efficient deployment, monitoring, and updating of ML and AI workloads, with a hub-and-spoke architecture for local inference and centralized training.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Power

If data is transmitted to centralized data centers for processing, then processing capability is improved, but latency increases and bandwidth usage increases

Engineering Contradiction:

Improveprocessing capabilityVSAvoidlatency

Core Design Contradiction:

PowerVSLoss of time

Solution Approach 1:

The system segments the centralized processing function into distributed edge nodes deployed at multiple locations. Each edge node can independently process data locally, eliminating the need for all data to travel to a single centralized data center, thereby reducing latency while maintaining processing capability.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The architecture transitions from a single centralized processing dimension to a multi-dimensional distributed processing model where edge nodes operate at various locations throughout the network. This spatial distribution enables parallel processing across multiple dimensions, reducing the time required for data transmission and processing.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Power

If data is transmitted to centralized data centers for processing, then processing capability is improved, but bandwidth usage increases

Engineering Contradiction:

Improveprocessing capabilityVSAvoidbandwidth usage

Core Design Contradiction:

PowerVSQuantity of substance

Solution Approach 1:

The system extracts processing functionality from the centralized data center and deploys it at edge nodes closer to data sources. This extraction allows data to be processed locally without requiring large amounts of bandwidth for transmission to centralized facilities, while still providing powerful processing capabilities through distributed compute resources.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

Each edge node is equipped with local processing capabilities tailored to handle data from its specific location. This local quality approach enables data to be processed at the source without requiring extensive bandwidth consumption for transmission to remote centralized centers, optimizing the balance between processing power and bandwidth usage.

Inventive Principle:

Principle #3Local quality

3Device complexity

If centralized processing is used, then data processing is simplified, but data privacy and network security are worsened

Engineering Contradiction:

Improvedata processing complexityVSAvoiddata privacy and network security

Core Design Contradiction:

Device complexityVSObject-affected harmful factors

Solution Approach 1:

The system segments data processing into distributed edge nodes that handle data locally, reducing the amount of sensitive data that needs to traverse the network and be stored in centralized facilities. This segmentation maintains processing simplicity at each node while enhancing overall data privacy and network security through reduced data exposure.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Edge nodes serve as intermediary processing points between data sources and the cloud. These intermediaries perform data processing and filtering locally, reducing the volume of data that needs to be transmitted and stored in centralized locations, thereby maintaining processing simplicity while improving data privacy and security.

Inventive Principle:

Principle #24Intermediary (Mediator)

4Loss of time

If edge computing is implemented, then latency is reduced, but device complexity increases

Engineering Contradiction:

ImprovelatencyVSAvoidsystem complexity

Core Design Contradiction:

Loss of timeVSDevice complexity

Solution Approach 1:

The edge nodes are designed as universal, multi-functional units that can perform various processing tasks, manage local data, and communicate with the cloud. This universality simplifies the overall system architecture by using standardized components rather than requiring complex custom solutions at each edge location, thereby reducing latency without proportionally increasing complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250278308A1Cloud-based fleet and asset management for edge computing of machine learning and artificial intelligence workloads

Publication Date: 2025.09.04 ARMADA SYST INC

AI summary

A method can include receiving monitoring information associated with a machine learning (ML) or artificial intelligence (AI) workload implemented by an edge compute unit of a plurality of edge compute units. Status information corresponding to a plurality of connected edge assets can be received, the plurality of edge compute units and connected edge assets included in a fleet of edge devices. A remote fleet management graphical user interface (GUI) can display a portion of the monitoring or status information for a subset of the fleet of edge devices, based on a user selection input, and can receive a user configuration input indicative of an updated configuration associated with at least one edge compute unit of the fleet. A cloud computing environment can transmit control information corresponding to the updated configuration to the at least one edge compute unit.